Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8982
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "shack."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "shack" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppo
    -0.74
    osate
    -0.72
    assic
    -0.71
    cker
    -0.69
    endars
    -0.66
    ague
    -0.66
    ppa
    -0.65
    icter
    -0.65
    teness
    -0.64
    ocious
    -0.63
    POSITIVE LOGITS
    eering
    1.03
    lain
    0.94
    yrinth
    0.93
    nai
    0.92
    eers
    0.91
    nesses
    0.88
    mone
    0.87
    intosh
    0.85
    ledge
    0.84
    neys
    0.84
    Activations Density 0.042%

    No Known Activations